Sökning: id:"swepub:oai:research.chalmers.se:7161d705-057c-44bf-af73-c84f499647ac" >
Activation sparsity...
Activation sparsity and dynamic pruning for split computing in edge AI
-
- Haberer, Janek (författare)
- Christian-Albrechts-Universität zu Kiel,University of Kiel
-
- Landsiedel, Olaf, 1979 (författare)
- Christian-Albrechts-Universität zu Kiel,University of Kiel,Chalmers tekniska högskola,Chalmers University of Technology
-
(creator_code:org_t)
- 2022-12-06
- 2022
- Engelska.
-
Ingår i: DistributedML 2022 - Proceedings of the 3rd International Workshop on Distributed Machine Learning, Part of CoNEXT 2022. - New York, NY, USA : ACM. ; , s. 30-36
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- Deep neural networks are getting larger and, therefore, harder to deploy on constrained IoT devices. Split computing provides a solution by splitting a network and placing the first few layers on the IoT device. The output of these layers is transmitted to the cloud where inference continues. Earlier works indicate a degree of high sparsity in intermediate activation outputs, this paper analyzes and exploits activation sparsity to reduce the network communication overhead when transmitting intermediate data to the cloud. Specifically, we analyze the intermediate activations of two early layers in ResNet-50 on CIFAR-10 and ImageNet, focusing on sparsity to guide the process of choosing a splitting point. We employ dynamic pruning of activations and feature maps and find that sparsity is very dependent on the size of a layer, and weights do not correlate with activation sparsity in convolutional layers. Additionally, we show that sparse intermediate outputs can be compressed by a factor of 3.3X at an accuracy loss of 1.1% without any fine-tuning. When adding fine-tuning, the compression factor increases up to 14X at a total accuracy loss of 1%.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorteknik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Engineering (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Telekommunikation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Telecommunications (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)
Nyckelord
- Edge Computing
- Offloading
- Feature Map Pruning
- Activation Sparsity
- Deep Learning
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)